© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · GPT-OSS BatchTopK SAEs
    5. GPT-OSS-20B
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 91299
    Prev
    Next
    INDEX
    Explanations

    repeated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-gpt-oss-20b/resid_post_layer_11/trainer_0
    Dataset (Dashboard)
    Various
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hunter
    -0.08
    ರ್ಷ
    -0.08
    综合
    -0.08
    281
    -0.08
    ತ್ತರ
    -0.08
    ದುವ
    -0.07
    ರ್�
    -0.07
     collapse
    -0.07
    иками
    -0.07
    -workers
    -0.07
    POSITIVE LOGITS
    uous
    0.10
     redundancy
    0.09
    itive
    0.08
    itives
    0.08
     redund
    0.08
     redundant
    0.08
    _COPY
    0.08
     повтор
    0.08
     একই
    0.08
    uplic
    0.08
    Activations Density 0.010%

    No Known Activations